Ë §¥'h—jãó—ddlmZddlZddlZddlmZmZmZddlm Z m Z mZmZm Z ddlZddlZddlmZddlmZmZmZddlmZmZmZmZmZddlmZej<e«Z dd „Z!Gd „dee«Z"y) é)ÚannotationsN)ÚIterableÚMappingÚSequence)ÚAnyÚLiteralÚOptionalÚUnionÚcast)Ú Embeddings)Úfrom_envÚget_pydantic_field_namesÚsecret_from_env)Ú BaseModelÚ ConfigDictÚFieldÚ SecretStrÚmodel_validator)ÚSelfcó —t|«Dcgc]}g‘Œ}}t|«Dcgc]}g‘Œ}}tt|««D]S}|rt||«dk(rŒ|||j||«|||jt||««ŒUg} t|«D]Ä}||} t| «dk(r| jd«Œ(t| «dk(r| j| d«ŒKt||«}t | ŽDcgc]$}td„t |||«D««|z‘Œ&} }td„| D««dz}| j| Dcgc]}||z‘Œ c}«ŒÆ| Scc}wcc}wcc}wcc}w)Nérc3ó,K—|]\}}||z–—Œyw©N©)Ú.0ÚvalÚweights úg/home/kushmeetdev/Regenta/Chatbot/venv/lib/python3.12/site-packages/langchain_openai/embeddings/base.pyú z6_process_batched_chunked_embeddings..?s èø€òá#˜˜Vð˜&•Lñùs‚c3ó&K—|] }|dz–—Œyw)éNr)rrs rrz6_process_batched_chunked_embeddings..Isèø€Ò6 s˜C FÑ6ùó‚gà?)ÚrangeÚlenÚappendÚsumÚzip)Ú num_textsÚtokensÚbatched_embeddingsÚindicesÚ skip_emptyÚ_ÚresultsÚnum_tokens_in_batchÚiÚ embeddingsÚ_resultÚtotal_weightÚ embeddingÚaverageÚ magnituders rÚ#_process_batched_chunked_embeddingsr7s¿€ô5:¸)Ó4DÖ'E¨qªÐ'E€GÐ'Eô 9>¸iÓ8HÖ+I°1ªBÐ+IÐÐ+Iä ”3w“<Ó ò?ˆÙœ#Ð0°Ñ3Ó4¸Ò9ØØ˜‘ Ñ×"Ñ"Ð#5°aÑ#8Ô9Ø˜G A™JÑ'×.Ñ.¬s°6¸!±9«~Õ>ð ?ð/1€JÜ 9Ó ò Dˆà%,¨Q¡Zˆäˆw‹<˜1Òð ×Ñ˜dÔ#Øä ‹\˜QÒ à×Ñ˜g a™jÔ)ØôÐ2°1Ñ5Ó6ˆLô"% g ö ðôñä'*¨9Ð6IÈ!Ñ6LÓ'Môóðó ðˆGðôÑ6¨gÔ6Ó6¸#Ñ=ˆIØ×Ñ¸'ÖB°3˜s Y›ÒBÕCðA DðDÐùòc(Fùò ,Jùò<ùòCsŽ E1¦ E6Ä)E;ÅF cóä—eZdZUdZedd¬«Zded<edd¬«Zded<dZd ed <dZ ded< eZ d ed<eedd¬«d¬«Zd ed< ededd¬«¬«Z d ed< eedd¬«¬«Zd ed<eedd¬«¬«Zd ed<dZded< ed ed!d¬«¬«Zd"ed#< ed$ed%d&gd¬«¬«Zd ed'< dZd(ed)<dZd*ed+<d,Zded-< d.Zded/< edd0¬1«Zd2ed3< dZded4<dZd5ed6< dZd ed7< d8Zd5ed9< ee¬«Zd:ed;< d8Zd5ed<< dZ d=ed><dZ!d?ed@<dAZ"dedB< dCZ#dedD< dZ$dEedF< dZ%dEedG< dZ&d5edH< e'dIddJ¬K«Z(e)dL¬M«e*dZdN„««Z+e)dO¬M«d[dP„«Z,e-d\dQ„«Z. d]dR„Z/ddSœ d^dT„Z0ddSœ d^dU„Z1 d_ d`dV„Z2 d_ d`dW„Z3dadX„Z4dadY„Z5y)bÚOpenAIEmbeddingsuè OpenAI embedding model integration. Setup: Install ``langchain_openai`` and set environment variable ``OPENAI_API_KEY``. .. code-block:: bash pip install -U langchain_openai export OPENAI_API_KEY="your-api-key" Key init args â€” embedding params: model: str Name of OpenAI model to use. dimensions: Optional[int] = None The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. Key init args â€” client params: api_key: Optional[SecretStr] = None OpenAI API key. organization: Optional[str] = None OpenAI organization ID. If not passed in will be read from env var OPENAI_ORG_ID. max_retries: int = 2 Maximum number of retries to make when generating. request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None Timeout for requests to OpenAI completion API See full list of supported init args and their descriptions in the params section. Instantiate: .. code-block:: python from langchain_openai import OpenAIEmbeddings embed = OpenAIEmbeddings( model="text-embedding-3-large" # With the `text-embedding-3` class # of models, you can specify the size # of the embeddings you want returned. # dimensions=1024 ) Embed single text: .. code-block:: python input_text = "The meaning of life is 42" vector = embeddings.embed_query("hello") print(vector[:3]) .. code-block:: python [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915] Embed multiple texts: .. code-block:: python vectors = embeddings.embed_documents(["hello", "goodbye"]) # Showing only the first 3 coordinates print(len(vectors)) print(vectors[0][:3]) .. code-block:: python 2 [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915] Async: .. code-block:: python await embed.aembed_query(input_text) print(vector[:3]) # multiple: # await embed.aembed_documents(input_texts) .. code-block:: python [-0.009100092574954033, 0.005071679595857859, -0.0029193938244134188] NT)ÚdefaultÚexcluderÚclientÚasync_clientztext-embedding-ada-002ÚstrÚmodelú Optional[int]Ú dimensionsz Optional[str]Ú deploymentÚOPENAI_API_VERSION)r:Úapi_version)Údefault_factoryÚaliasÚopenai_api_versionÚbase_urlÚOPENAI_API_BASE)rFrEÚopenai_api_baseÚOPENAI_API_TYPE)rEÚopenai_api_typeÚOPENAI_PROXYÚopenai_proxyiÿÚintÚembedding_ctx_lengthÚapi_keyÚOPENAI_API_KEYzOptional[SecretStr]Úopenai_api_keyÚorganizationÚ OPENAI_ORG_IDÚOPENAI_ORGANIZATIONÚopenai_organizationz%Union[Literal['all'], set[str], None]Úallowed_specialz4Union[Literal['all'], set[str], Sequence[str], None]Údisallowed_specialièÚ chunk_sizer!Úmax_retriesÚtimeout)r:rFz0Optional[Union[float, tuple[float, float], Any]]Úrequest_timeoutÚheadersÚboolÚtiktoken_enabledÚtiktoken_model_nameFÚshow_progress_barúdict[str, Any]Úmodel_kwargsr,zUnion[Mapping[str, str], None]Údefault_headersz!Union[Mapping[str, object], None]Ú default_queryéÚretry_min_secondséÚretry_max_secondszUnion[Any, None]Úhttp_clientÚhttp_async_clientÚcheck_embedding_ctx_lengthÚforbidr)ÚextraÚpopulate_by_nameÚprotected_namespacesÚbefore)Úmodec ó`—t|«}|jdi«}t|«D]M}||vrtd|›d«‚||vsŒt j d|›d|›d|›d«|j |«||<ŒO|j|j««}|rtd|›d «‚||d<|S) z>Build extra kwargs from additional params that were passed in.rdzFound z supplied twice.z WARNING! z/ is not default parameter. zJ was transferred to model_kwargs. Please confirm that z is what you intended.zParameters za should be specified explicitly. Instead they were passed in as part of `model_kwargs` parameter.) rÚgetÚlistÚ ValueErrorÚwarningsÚwarnÚpopÚintersectionÚkeys)ÚclsÚvaluesÚall_required_field_namesroÚ field_nameÚinvalid_model_kwargss rÚbuild_extrazOpenAIEmbeddings.build_extrasì€ô$<¸CÓ#@Ð Ø— ‘ ˜>¨2Ó.ˆÜ˜v›,ò ;ˆJØ˜UÑ"Ü 6¨*¨Ð5EÐ!FÓGÐGØÐ!9Ò9Ü— ‘ Ø! * ð.ØLð!)Ø)3¨Ð4JðNôð %+§J¡J¨zÓ$:jÒ!ð ;ð 8×DÑDÀUÇZÁZÃ\ÓRÐÙÜØÐ2Ð3ð4SðTóð ð "'ˆˆ~ÑØˆ óÚaftercó4—|jdvrtd«‚|jr|jj«nd|j|j |j|j|j|jdœ}|jrP|js|jr8|j}|j}|j}td|›d|›d|›«‚|jsr|jr2|js& ddl}|j!|j¬ «|_d|ji}t#j$di|¤|¤Žj&|_ |j(sr|jr2|js& ddl}|j+|j¬ «|_d|ji}t#j,di|¤|¤Žj&|_|S#t$r}td «|‚d}~wwxYw#t$r}td «|‚d}~wwxYw) z?Validate that api key and python package exists in environment.)ÚazureÚazure_adÚazureadzEIf you are using Azure, please use the `AzureOpenAIEmbeddings` class.N)rQrTrHr\r[rerfzwCannot specify 'openai_proxy' if one of 'http_client'/'http_async_client' is already specified. Received: openai_proxy=z http_client=z http_async_client=rzRCould not import httpx python package. Please install it with `pip install httpx`.)Úproxyrkr)rLrwrSÚget_secret_valuerWrJr]r[rerfrNrkrlr<ÚhttpxÚImportErrorÚClientÚopenaiÚOpenAIr1r=ÚAsyncClientÚAsyncOpenAI) ÚselfÚ client_paramsrNrkrlr‹ÚeÚ sync_specificÚasync_specifics rÚvalidate_environmentz%OpenAIEmbeddings.validate_environments-€ð×ÑÐ#CÑCÜð@óð ð;?×:MÒ:M×#Ñ#×4Ñ4Ô6ÐSWà ×4Ñ4Ø×,Ñ,Ø×+Ñ+Ø×+Ñ+Ø#×3Ñ3Ø!×/Ñ/ñ ˆ ð×Ò $×"2Ò"2°d×6LÒ6LØ×,Ñ,ˆLØ×*Ñ*ˆKØ $× 6Ñ 6ÐÜð!à/ K >Ð1FÐ4EÐ3GðIóð ð {Š{Ø× Ò ¨×)9Ò)9ðÛ ð$)§<¡<°d×6GÑ6G <Ó#HÔ Ø*¨D×,<Ñ,<Ð=ˆMÜ Ÿ-™-ÑI¨-ÐI¸=ÑI×TÑTˆDŒKØ× Ò Ø× Ò ¨×)?Ò)?ðÛ ð*/×):Ñ):À×ARÑARÐ):Ó)SÔ&Ø+¨T×-CÑ-CÐDˆNÜ &× 2Ñ 2ñ!Øð!à ñ!÷‰jð Ôðˆøô/#òÜ%ðFóððûðûô#òÜ%ðFóððûðús0ÄG ÆG=Ç G:Ç)G5Ç5G:Ç= HÈHÈHcóp—d|ji|j¥}|j|j|d<|S)Nr?rA)r?rdrA)r’Úparamss rÚ_invocation_paramsz#OpenAIEmbeddings._invocation_paramsXs8€à §¡ÐA¨t×/@Ñ/@ÐAˆØ?‰?Ð&Ø#'§?¡?ˆF<Ñ Øˆ rƒcó2—g}g}|jxs|j}|js« ddlm}|j|¬«}t|«D]‚\}} |j| d¬«} tdt| «|j«D]G}| |||jz}|j|«} |j| «|j|«ŒIŒ„n tj |«}|j&|j(dœj+«Dcic] \}}|||“Œ}}}t|«D]°\}} |jj-d «r| j/d d«} |r|j| fi|¤Ž}n|j1| «}tdt|«|j«D]4}|j||||jz«|j|«Œ6Œ²|j2r$ ddlm}|tdt|«|««}ntdt|«|«}|||fS#t $rt d«‚wxYw#t"$rtj$d«}YŒ~wxYwcc}}w#t $rtdt|«|«}YŒiwxYw) aí Take the input `texts` and `chunk_size` and return 3 iterables as a tuple: We have `batches`, where batches are sets of individual texts we want responses from the openai api. The length of a single batch is `chunk_size` texts. Each individual text is also split into multiple texts based on the `embedding_ctx_length` parameter (based on number of tokens). This function returns a 3-tuple of the following: _iter: An iterable of the starting index in `tokens` for each *batch* tokens: A list of tokenized texts, where each text has already been split into sub-texts based on the `embedding_ctx_length` parameter. In the case of tiktoken, this is a list of token arrays. In the case of HuggingFace transformers, this is a list of strings. indices: An iterable of the same length as `tokens` that maps each token-array to the index of the original text in `texts`. r)Ú AutoTokenizerz¡Could not import transformers python package. This is needed for OpenAIEmbeddings to work without `tiktoken`. Please install it with `pip install transformers`. )Úpretrained_model_name_or_pathF)Úadd_special_tokensÚcl100k_base)rXrYÚ001ú ú )Útqdm)rar?r`ÚtransformersrœrŒrwÚfrom_pretrainedÚ enumerateÚencoder#r$rPÚdecoder%ÚtiktokenÚencoding_for_modelÚKeyErrorÚget_encodingrXrYÚitemsÚendswithÚreplaceÚencode_ordinaryrbÚ tqdm.autor£)r’ÚtextsrZr)r+Ú model_namerœÚ tokenizerr0ÚtextÚ tokenizedÚjÚtoken_chunkÚ chunk_textÚencodingÚkÚvÚencoder_kwargsÚtokenr£Ú_iters rÚ _tokenizezOpenAIEmbeddings._tokenize_sµ€ð./1ˆØˆØ×-Ñ-Ò;°·±ˆ ð×$Ò$ð Ý6ð&×5Ñ5Ø.8ð6óˆIô% UÓ+ò &‘4à'0×'7Ñ'7¸ÐQVÐ'7Ó'W ô˜q¤# i£.°$×2KÑ2KÓLò&AØ-6Ø˜A × 9Ñ 9Ñ9ð.Kð '0×&6Ñ&6°{Ó&CJØ—M‘M *Ô-Ø—N‘N 1Õ%ñ&ò &ð @Ü#×6Ñ6°zÓBð(,×';Ñ';Ø*.×*AÑ*Añ÷‘%“'÷.áAqð=ð1‘ð.ˆNñ.ô% UÓ+ò &‘4Ø—:‘:×&Ñ& uÔ-ð Ÿ<™<¨¨cÓ2Dá!Ø+˜HŸO™O¨DÑC°NÑC‘Eà$×4Ñ4°TÓ:Eô˜q¤# e£*¨d×.GÑ.GÓHò&AØ—M‘M %¨¨A°×0IÑ0IÑ,IÐ"JÔKØ—N‘N 1Õ%ñ&ð &ð"×!Ò!ð :Ý*á"&¤u¨Q´°F³¸ZÓ'HÓ"I‘ô˜!œS ›[¨*Ó5ˆEØf˜gÐ%Ð%øôò Ü ðVóðð ûô6ò @Ü#×0Ñ0°Ó?“ð @üó.øô<ò :Ü˜a¤ V£¨jÓ9’ð :ús5¬H1ÃI ÄI.Ç3"I4È1IÉ I+É*I+É4JÊJ)rZc óØ‡‡‡—|xs‰j}i‰j¥|¥Š‰j||«\}}}g} |D]a} ‰jjdd|| | |zi‰¤Ž}t|t«s|j«}| jd„|dD««Œctt|«|| |‰j«}dŠdˆˆˆfd„} |Dcgc] }||n| «‘Œc}Scc}w)al Generate length-safe embeddings for a list of texts. This method handles tokenization and embedding generation, respecting the set embedding context length and chunk size. It supports both tiktoken and HuggingFace tokenizer based on the tiktoken_enabled flag. Args: texts (List[str]): A list of texts to embed. engine (str): The engine or model to use for embeddings. chunk_size (Optional[int]): The size of chunks for processing embeddings. Returns: List[List[float]]: A list of embeddings for each input text. Úinputc3ó&K—|] }|d–—Œyw©r4Nr©rÚrs rrz.âóèø€Ò%O¸ a¨¥nÑ%Oùr"ÚdataNcóž•—‰€I‰jjdddi‰¤Ž}t|t«s|j «}|dddŠ‰S©NrÂÚrÈrr4r)r<ÚcreateÚ isinstanceÚdictÚ model_dump©Úaverage_embeddedÚ_cached_empty_embeddingÚ client_kwargsr’s €€€rÚempty_embeddingzBOpenAIEmbeddings._get_len_safe_embeddings..empty_embeddingés]ø€à&Ð.Ø#5 4§;¡;×#5Ñ#5Ñ#P¸BÐ#PÀ-Ñ#PÐ Ü!Ð"2´DÔ9Ø'7×'BÑ'BÓ'DÐ$Ø*:¸6Ñ*BÀ1Ñ*EÀkÑ*RÐ'Ø*Ð*rƒr©Úreturnúlist[float])rZršrÀr<rÌrÍrÎrÏÚextendr7r$r,©r’r²ÚenginerZÚkwargsÚ_chunk_sizer¿r)r+r*r0Úresponser1rÔr”rÒrÓs` @@rÚ_get_len_safe_embeddingsz)OpenAIEmbeddings._get_len_safe_embeddingsÁsú€ð.!Ò3 D§O¡OˆØ=˜4×2Ñ2Ð=°fÐ=ˆ Ø!%§¡°°{Ó!CÑˆˆvwØ02ÐØò PˆAØ)t—{‘{×)Ñ)ñØ˜Q [¡Ð1ðØ5BñˆHô˜h¬Ô-Ø#×.Ñ.Ó0Ø×%Ñ%Ñ%O¸hÀvÑ>NÔ%OÕOð Pô9Ü‹J˜Ð 2°G¸T¿_¹_ó ˆ ð:>Ð÷ +ðDNÖN¸aQ]‘©Ó(9Ñ9ÒNÐNùÒNsÃC'c ‹ó0‡‡‡K—|xs‰j}i‰j¥|¥Š‰j||«\}}}g} tdt |«|«D]i} ‰j jdd|| | |zi‰¤Žƒd{–—†}t|t«s|j«}| jd„|dD««Œktt |«|| |‰j«}dŠdˆˆˆfd„} |Dcgc]}||n| «ƒd{–—†‘Œc}S7ŒŽ7Œcc}ww) aŒ Asynchronously generate length-safe embeddings for a list of texts. This method handles tokenization and asynchronous embedding generation, respecting the set embedding context length and chunk size. It supports both `tiktoken` and HuggingFace `tokenizer` based on the tiktoken_enabled flag. Args: texts (List[str]): A list of texts to embed. engine (str): The engine or model to use for embeddings. chunk_size (Optional[int]): The size of chunks for processing embeddings. Returns: List[List[float]]: A list of embeddings for each input text. rrÂNc3ó&K—|] }|d–—ŒywrÄrrÅs rrz=OpenAIEmbeddings._aget_len_safe_embeddings..rÇr"rÈc“óº•K—‰€Q‰jjdddi‰¤Žƒd{–—†}t|t«s|j «}|dddŠ‰S7Œ1wrÊ)r=rÌrÍrÎrÏrÐs €€€rrÔzCOpenAIEmbeddings._aget_len_safe_embeddings..empty_embedding swøèø€à&Ð.Ø)A¨×):Ñ):×)AÑ)Añ*Øð*Ø -ñ*÷$Ð ô"Ð"2´DÔ9Ø'7×'BÑ'BÓ'DÐ$Ø*:¸6Ñ*BÀ1Ñ*EÀkÑ*RÐ'Ø*Ð*ð $úsƒ$A§A¨2ArrÕ) rZršrÀr#r$r=rÌrÍrÎrÏrØr7r,rÙs` @@rÚ_aget_len_safe_embeddingsz*OpenAIEmbeddings._aget_len_safe_embeddingsös2úèø€ð0!Ò3 D§O¡OˆØ=˜4×2Ñ2Ð=°fÐ=ˆ Ø!%§¡°°{Ó!CÑˆˆvwØ02ÐÜqœ#˜f›+ {Ó3ò PˆAØ5˜T×.Ñ.×5Ñ5ñØ˜Q [¡Ð1ðØ5Bñ÷ˆHô˜h¬Ô-Ø#×.Ñ.Ó0Ø×%Ñ%Ñ%O¸hÀvÑ>NÔ%OÕOð Pô9Ü‹J˜Ð 2°G¸T¿_¹_ó ˆ ð:>Ð÷ +ðJTÖTÀAQ]‘©oÓ.?×(?Ñ?ÒTÐTð1øð0)@úÒTùs7…A9DÁ>D Á?A1DÃ0DÄD ÄDÄ DÄDÄDc ó¶—|xs|j}i|j¥|¥}|js~g}tdt |«|«D]a}|j jdd||||zi|¤Ž}t|t«s|j«}|jd„|dD««Œc|Stt|j«} |j|f| |dœ|¤ŽS)aœCall out to OpenAI's embedding endpoint for embedding search docs. Args: texts: The list of texts to embed. chunk_size: The chunk size of embeddings. If None, will use the chunk size specified by the class. kwargs: Additional keyword arguments to pass to the embedding API. Returns: List of embeddings, one for each text. rrÂc3ó&K—|] }|d–—ŒywrÄrrÅs rrz3OpenAIEmbeddings.embed_documents..Eóèø€Ò!K°Q ! K¥.Ñ!Kùr"rÈ©rÚrZr)rZršrmr#r$r<rÌrÍrÎrÏrØrr>rBrÞ© r’r²rZrÛÚchunk_size_rÓr1r0rÝrÚs rÚembed_documentsz OpenAIEmbeddings.embed_documents-sû€ð!Ò3 D§O¡OˆØ=˜4×2Ñ2Ð=°fÐ=ˆ Ø×.Ò.Ø,.ˆJÜ˜1œc %›j¨+Ó6ò LØ-˜4Ÿ;™;×-Ñ-ñØ A¨¡OÐ4ðØ8Eñô" (¬DÔ1Ø'×2Ñ2Ó4HØ×!Ñ!Ñ!K¸(À6Ñ:JÔ!KÕKð LðÐô”c˜4Ÿ?™?Ó+ˆØ,ˆt×,Ñ,Øð Ø ¨Zñ Ø;Añ ð rƒc ‹óæK—|xs|j}i|j¥|¥}|js†g}tdt |«|«D]i}|j jdd||||zi|¤Žƒd{–—†}t|t«s|j«}|jd„|dD««Œk|Stt|j«} |j|f| |dœ|¤Žƒd{–—†S7Œ{7Œw)a¢Call out to OpenAI's embedding endpoint async for embedding search docs. Args: texts: The list of texts to embed. chunk_size: The chunk size of embeddings. If None, will use the chunk size specified by the class. kwargs: Additional keyword arguments to pass to the embedding API. Returns: List of embeddings, one for each text. rrÂNc3ó&K—|] }|d–—ŒywrÄrrÅs rrz4OpenAIEmbeddings.aembed_documents..grår"rÈrær)rZršrmr#r$r=rÌrÍrÎrÏrØrr>rBrârçs rÚaembed_documentsz!OpenAIEmbeddings.aembed_documentsOsèø€ð!Ò3 D§O¡OˆØ=˜4×2Ñ2Ð=°fÐ=ˆ Ø×.Ò.Ø,.ˆJÜ˜1œc %›j¨+Ó6ò LØ!9 ×!2Ñ!2×!9Ñ!9ñ"Ø A¨¡OÐ4ð"Ø8Eñ"÷ô" (¬DÔ1Ø'×2Ñ2Ó4HØ×!Ñ!Ñ!K¸(À6Ñ:JÔ!KÕKð LðÐô”c˜4Ÿ?™?Ó+ˆØ3T×3Ñ3Øð Ø ¨Zñ Ø;Añ ÷ ð ðøð ús%‚A/C1Á1C-Á2A6C1Ã(C/Ã)C1Ã/C1có0—|j|gfi|¤ŽdS)aCall out to OpenAI's embedding endpoint for embedding query text. Args: text: The text to embed. kwargs: Additional keyword arguments to pass to the embedding API. Returns: Embedding for the text. r)ré)r’rµrÛs rÚembed_queryzOpenAIEmbeddings.embed_queryqs#€ð$ˆt×#Ñ# T FÑ5¨fÑ5°aÑ8Ð8rƒc‹óPK—|j|gfi|¤Žƒd{–—†}|dS7Œ w)a Call out to OpenAI's embedding endpoint async for embedding query text. Args: text: The text to embed. kwargs: Additional keyword arguments to pass to the embedding API. Returns: Embedding for the text. Nr)rì)r’rµrÛr1s rÚaembed_queryzOpenAIEmbeddings.aembed_query}s4èø€ð1˜4×0Ñ0°$°ÑB¸6ÑB×Bˆ Ø˜!‰}ÐðCús‚&š$› &)r~rcrÖr)rÖr)rÖrc)r²ú list[str]rZrOrÖzrZr@rÛrrÖúlist[list[float]]r)r²rñrZr@rÛrrÖrò)rµr>rÛrrÖr×)6Ú__name__Ú __module__Ú__qualname__Ú__doc__rr<Ú__annotations__r=r?rArBr rGrJrLrNrPrrSrWrXrYrZr[r]r^r`rarbrÎrdr,rerfrhrjrkrlrmrÚmodel_configrÚclassmethodr‚r—ÚpropertyršrÀrÞrârérìrîrðrrƒrr9r9Osµ…ñOñb ¨dÔ3€FˆCÓ3Ù d°DÔ9€L#Ó9Ø)€Eˆ3Ó)Ø $€J Ó$ðð !&€J Ó%á(-Ù Ð!5¸tÔDØô)Ð˜ óðTá%*Ø©(Ð3DÈdÔ*Sô&€O]óðñ&+Ù Ð!2¸DÔAô&€O]óñ#(Ù ¸Ô>ô#€L-óð!%Ð˜#Ó$Ø8Ù*/Ø©Ð9IÐSWÔ)Xô+€NÐ'óðPÙ).ØÙ Ø Ð3Ð4¸dô ô*Ð˜óðOØ=A€OÐ:ÓAØOSÐÐLÓSØ€JÓØ8Ø€KÓØ<ÙHMØ˜IôI€OÐEóðà€GˆSÓØ!ÐdÓ!ðGà)-Ð˜Ó-ðJð$ÐtÓ#Ø8Ù#(¸Ô#>€L.Ó>ØVØ€JÓð!à6:€OÐ3Ó:Ø7;€MÐ4Ó;ðÐsÓØ7ØÐsÓØ7Ø$(€KÐ!Ó(ðð+/ÐÐ'Ó.ðSà'+Ð Ó+ð-ñØ¨ÀBô€Lñ˜(Ô#Øòóó$ðñ2˜'Ô"ò7ó#ð7ðròóðð^&Øð^&Ø,/ð^&à Eó^&ðN%)ñ1Oàð1Oðð 1Oð "ð1Oðð 1Oð ó1Oðt%)ñ5Uàð5Uðð 5Uð "ð5Uðð 5Uð ó5Uðp=Að Øð Ø,9ð ØLOð à ó ðF=Að Øð Ø,9ð ØLOð à ó óD 9ôrƒr9)r(rOr)zlist[Union[list[int], str]]r*ròr+z list[int]r,r_rÖzlist[Optional[list[float]]])#Ú __future__rÚloggingrxÚcollections.abcrrrÚtypingrrr r rrŽr©Úlangchain_core.embeddingsrÚlangchain_core.utilsr rrÚpydanticrrrrrÚtyping_extensionsrÚ getLoggerróÚloggerr7r9rrƒrúrs’ðÝ"ãÛß7Ñ7ß6Õ6ã ÛÝ0ßTÑTßMÕMÝ"à ˆ× Ñ ˜8Ó $€ð:Øð:à'ð:ð*ð:ðð :ð ð:ð!ó :ôzyy *õyrƒ